diff options
Diffstat (limited to 'tools/perf')
36 files changed, 660 insertions, 242 deletions
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 27fc3617c6a4..5054d9147f0f 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -430,6 +430,10 @@ that gets then processed, possibly via a perf script, to decide if that particular perf.data snapshot should be kept or not. Implies --timestamp-filename, --no-buildid and --no-buildid-cache. +The reason for the latter two is to reduce the data file switching +overhead. You can still switch them on with: + + --switch-output --no-no-buildid --no-no-buildid-cache --dry-run:: Parse options then exit. --dry-run can be used to detect errors in cmdline diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt index 7775b1eb2bee..76173969ab80 100644 --- a/tools/perf/Documentation/perf-sched.txt +++ b/tools/perf/Documentation/perf-sched.txt @@ -132,6 +132,10 @@ OPTIONS for 'perf sched timehist' --migrations:: Show migration events. +-I:: +--idle-hist:: + Show idle-related events only. + --time:: Only analyze samples within given time window: <start>,<stop>. Times have the format seconds.microseconds. If start is not given (i.e., time diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 8f1c258b151a..8bb16aa9d661 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -100,7 +100,7 @@ LC_NUMERIC=C export LC_COLLATE LC_NUMERIC ifeq ($(srctree),) -srctree := $(patsubst %/,%,$(dir $(shell pwd))) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) srctree := $(patsubst %/,%,$(dir $(srctree))) #$(info Determined 'srctree' to be $(srctree)) endif @@ -201,6 +201,7 @@ goals := $(filter-out all sub-make, $(MAKECMDGOALS)) $(goals) all: sub-make sub-make: fixdep + @./check-headers.sh $(Q)$(MAKE) FIXDEP=1 -f Makefile.perf $(goals) else # force_fixdep @@ -404,99 +405,6 @@ export JEVENTS build := -f $(srctree)/tools/build/Makefile.build dir=. obj $(PERF_IN): prepare FORCE - @(test -f ../../include/uapi/linux/perf_event.h && ( \ - (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \ - || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true - @(test -f ../../include/linux/hash.h && ( \ - (diff -B ../include/linux/hash.h ../../include/linux/hash.h >/dev/null) \ - || echo "Warning: tools/include/linux/hash.h differs from kernel" >&2 )) || true - @(test -f ../../include/uapi/linux/hw_breakpoint.h && ( \ - (diff -B ../include/uapi/linux/hw_breakpoint.h ../../include/uapi/linux/hw_breakpoint.h >/dev/null) \ - || echo "Warning: tools/include/uapi/linux/hw_breakpoint.h differs from kernel" >&2 )) || true - @(test -f ../../arch/x86/include/asm/disabled-features.h && ( \ - (diff -B ../arch/x86/include/asm/disabled-features.h ../../arch/x86/include/asm/disabled-features.h >/dev/null) \ - || echo "Warning: tools/arch/x86/include/asm/disabled-features.h differs from kernel" >&2 )) || true - @(test -f ../../arch/x86/include/asm/required-features.h && ( \ - (diff -B ../arch/x86/include/asm/required-features.h ../../arch/x86/include/asm/required-features.h >/dev/null) \ - || echo "Warning: tools/arch/x86/include/asm/required-features.h differs from kernel" >&2 )) || true - @(test -f ../../arch/x86/include/asm/cpufeatures.h && ( \ - (diff -B ../arch/x86/include/asm/cpufeatures.h ../../arch/x86/include/asm/cpufeatures.h >/dev/null) \ - || echo "Warning: tools/arch/x86/include/asm/cpufeatures.h differs from kernel" >&2 )) || true - @(test -f ../../arch/x86/lib/memcpy_64.S && ( \ - (diff -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" ../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memcpy_64.S >/dev/null) \ - || echo "Warning: tools/arch/x86/lib/memcpy_64.S differs from kernel" >&2 )) || true - @(test -f ../../arch/x86/lib/memset_64.S && ( \ - (diff -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" ../arch/x86/lib/memset_64.S ../../arch/x86/lib/memset_64.S >/dev/null) \ - || echo "Warning: tools/arch/x86/lib/memset_64.S differs from kernel" >&2 )) || true - @(test -f ../../arch/arm/include/uapi/asm/perf_regs.h && ( \ - (diff -B ../arch/arm/include/uapi/asm/perf_regs.h ../../arch/arm/include/uapi/asm/perf_regs.h >/dev/null) \ - || echo "Warning: tools/arch/arm/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true - @(test -f ../../arch/arm64/include/uapi/asm/perf_regs.h && ( \ - (diff -B ../arch/arm64/include/uapi/asm/perf_regs.h ../../arch/arm64/include/uapi/asm/perf_regs.h >/dev/null) \ - || echo "Warning: tools/arch/arm64/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true - @(test -f ../../arch/powerpc/include/uapi/asm/perf_regs.h && ( \ - (diff -B ../arch/powerpc/include/uapi/asm/perf_regs.h ../../arch/powerpc/include/uapi/asm/perf_regs.h >/dev/null) \ - || echo "Warning: tools/arch/powerpc/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true - @(test -f ../../arch/x86/include/uapi/asm/perf_regs.h && ( \ - (diff -B ../arch/x86/include/uapi/asm/perf_regs.h ../../arch/x86/include/uapi/asm/perf_regs.h >/dev/null) \ - || echo "Warning: tools/arch/x86/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true - @(test -f ../../arch/x86/include/uapi/asm/kvm.h && ( \ - (diff -B ../arch/x86/include/uapi/asm/kvm.h ../../arch/x86/include/uapi/asm/kvm.h >/dev/null) \ - || echo "Warning: tools/arch/x86/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true - @(test -f ../../arch/x86/include/uapi/asm/kvm_perf.h && ( \ - (diff -B ../arch/x86/include/uapi/asm/kvm_perf.h ../../arch/x86/include/uapi/asm/kvm_perf.h >/dev/null) \ - || echo "Warning: tools/arch/x86/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true - @(test -f ../../arch/x86/include/uapi/asm/svm.h && ( \ - (diff -B ../arch/x86/include/uapi/asm/svm.h ../../arch/x86/include/uapi/asm/svm.h >/dev/null) \ - || echo "Warning: tools/arch/x86/include/uapi/asm/svm.h differs from kernel" >&2 )) || true - @(test -f ../../arch/x86/include/uapi/asm/vmx.h && ( \ - (diff -B ../arch/x86/include/uapi/asm/vmx.h ../../arch/x86/include/uapi/asm/vmx.h >/dev/null) \ - || echo "Warning: tools/arch/x86/include/uapi/asm/vmx.h differs from kernel" >&2 )) || true - @(test -f ../../arch/powerpc/include/uapi/asm/kvm.h && ( \ - (diff -B ../arch/powerpc/include/uapi/asm/kvm.h ../../arch/powerpc/include/uapi/asm/kvm.h >/dev/null) \ - || echo "Warning: tools/arch/powerpc/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true - @(test -f ../../arch/s390/include/uapi/asm/kvm.h && ( \ - (diff -B ../arch/s390/include/uapi/asm/kvm.h ../../arch/s390/include/uapi/asm/kvm.h >/dev/null) \ - || echo "Warning: tools/arch/s390/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true - @(test -f ../../arch/s390/include/uapi/asm/kvm_perf.h && ( \ - (diff -B ../arch/s390/include/uapi/asm/kvm_perf.h ../../arch/s390/include/uapi/asm/kvm_perf.h >/dev/null) \ - || echo "Warning: tools/arch/s390/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true - @(test -f ../../arch/s390/include/uapi/asm/sie.h && ( \ - (diff -B ../arch/s390/include/uapi/asm/sie.h ../../arch/s390/include/uapi/asm/sie.h >/dev/null) \ - || echo "Warning: tools/arch/s390/include/uapi/asm/sie.h differs from kernel" >&2 )) || true - @(test -f ../../arch/arm/include/uapi/asm/kvm.h && ( \ - (diff -B ../arch/arm/include/uapi/asm/kvm.h ../../arch/arm/include/uapi/asm/kvm.h >/dev/null) \ - || echo "Warning: tools/arch/arm/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true - @(test -f ../../arch/arm64/include/uapi/asm/kvm.h && ( \ - (diff -B ../arch/arm64/include/uapi/asm/kvm.h ../../arch/arm64/include/uapi/asm/kvm.h >/dev/null) \ - || echo "Warning: tools/arch/arm64/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true - @(test -f ../../include/asm-generic/bitops/arch_hweight.h && ( \ - (diff -B ../include/asm-generic/bitops/arch_hweight.h ../../include/asm-generic/bitops/arch_hweight.h >/dev/null) \ - || echo "Warning: tools/include/asm-generic/bitops/arch_hweight.h differs from kernel" >&2 )) || true - @(test -f ../../include/asm-generic/bitops/const_hweight.h && ( \ - (diff -B ../include/asm-generic/bitops/const_hweight.h ../../include/asm-generic/bitops/const_hweight.h >/dev/null) \ - || echo "Warning: tools/include/asm-generic/bitops/const_hweight.h differs from kernel" >&2 )) || true - @(test -f ../../include/asm-generic/bitops/__fls.h && ( \ - (diff -B ../include/asm-generic/bitops/__fls.h ../../include/asm-generic/bitops/__fls.h >/dev/null) \ - || echo "Warning: tools/include/asm-generic/bitops/__fls.h differs from kernel" >&2 )) || true - @(test -f ../../include/asm-generic/bitops/fls.h && ( \ - (diff -B ../include/asm-generic/bitops/fls.h ../../include/asm-generic/bitops/fls.h >/dev/null) \ - || echo "Warning: tools/include/asm-generic/bitops/fls.h differs from kernel" >&2 )) || true - @(test -f ../../include/asm-generic/bitops/fls64.h && ( \ - (diff -B ../include/asm-generic/bitops/fls64.h ../../include/asm-generic/bitops/fls64.h >/dev/null) \ - || echo "Warning: tools/include/asm-generic/bitops/fls64.h differs from kernel" >&2 )) || true - @(test -f ../../include/linux/coresight-pmu.h && ( \ - (diff -B ../include/linux/coresight-pmu.h ../../include/linux/coresight-pmu.h >/dev/null) \ - || echo "Warning: tools/include/linux/coresight-pmu.h differs from kernel" >&2 )) || true - @(test -f ../../include/uapi/asm-generic/mman-common.h && ( \ - (diff -B ../include/uapi/asm-generic/mman-common.h ../../include/uapi/asm-generic/mman-common.h >/dev/null) \ - || echo "Warning: tools/include/uapi/asm-generic/mman-common.h differs from kernel" >&2 )) || true - @(test -f ../../include/uapi/asm-generic/mman.h && ( \ - (diff -B -I "^#include <\(uapi/\)*asm-generic/mman-common.h>$$" ../include/uapi/asm-generic/mman.h ../../include/uapi/asm-generic/mman.h >/dev/null) \ - || echo "Warning: tools/include/uapi/asm-generic/mman.h differs from kernel" >&2 )) || true - @(test -f ../../include/uapi/linux/mman.h && ( \ - (diff -B -I "^#include <\(uapi/\)*asm/mman.h>$$" ../include/uapi/linux/mman.h ../../include/uapi/linux/mman.h >/dev/null) \ - || echo "Warning: tools/include/uapi/linux/mman.h differs from kernel" >&2 )) || true $(Q)$(MAKE) $(build)=perf $(JEVENTS_IN): FORCE @@ -796,9 +704,9 @@ install-tests: all install-gtk $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \ $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr' -install-bin: install-tools install-tests +install-bin: install-tools install-tests install-traceevent-plugins -install: install-bin try-install-man install-traceevent-plugins +install: install-bin try-install-man install-python_ext: $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)' diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 465012b320ee..6d9d6c40a916 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -48,7 +48,7 @@ static const struct option options[] = { }; static const char * const bench_futex_lock_pi_usage[] = { - "perf bench futex requeue <options>", + "perf bench futex lock-pi <options>", NULL }; diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 4b419631753d..f8ca7a4ebabc 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -208,7 +208,7 @@ static void compute_stats(struct c2c_hist_entry *c2c_he, static int process_sample_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel __maybe_unused, + struct perf_evsel *evsel, struct machine *machine) { struct c2c_hists *c2c_hists = &c2c.hists; @@ -379,7 +379,7 @@ static int symbol_width(struct hists *hists, struct sort_entry *se) static int c2c_width(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp __maybe_unused, - struct hists *hists __maybe_unused) + struct hists *hists) { struct c2c_fmt *c2c_fmt; struct c2c_dimension *dim; @@ -1127,7 +1127,7 @@ MEAN_ENTRY(mean_lcl_entry, lcl_hitm); MEAN_ENTRY(mean_load_entry, load); static int -cpucnt_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp, +cpucnt_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he) { struct c2c_hist_entry *c2c_he; @@ -1141,7 +1141,7 @@ cpucnt_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp, } static int -cl_idx_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp, +cl_idx_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he) { struct c2c_hist_entry *c2c_he; @@ -1155,7 +1155,7 @@ cl_idx_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp, } static int -cl_idx_empty_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp, +cl_idx_empty_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he) { int width = c2c_width(fmt, hpp, he->hists); @@ -1779,7 +1779,6 @@ static int c2c_hists__init(struct c2c_hists *hists, return hpp_list__parse(&hists->list, NULL, sort); } -__maybe_unused static int c2c_hists__reinit(struct c2c_hists *c2c_hists, const char *output, const char *sort) @@ -2658,7 +2657,7 @@ out: return err; } -static int parse_record_events(const struct option *opt __maybe_unused, +static int parse_record_events(const struct option *opt, const char *str, int unset __maybe_unused) { bool *event_set = (bool *) opt->value; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 9ff0db4e2d0c..933aeec46f4a 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -1199,7 +1199,7 @@ static int ui_init(void) BUG_ON(1); } - perf_hpp__register_sort_field(fmt); + perf_hpp__prepend_sort_field(fmt); return 0; } diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 35a02f8e5a4a..915869e00d86 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -655,7 +655,6 @@ static const struct { { "__GFP_RECLAIM", "R" }, { "__GFP_DIRECT_RECLAIM", "DR" }, { "__GFP_KSWAPD_RECLAIM", "KR" }, - { "__GFP_OTHER_NODE", "ON" }, }; static size_t max_gfp_len; diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index d1ce29be560e..cd7bc4d104e2 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -70,8 +70,8 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), - OPT_BOOLEAN('U', "--all-user", &all_user, "collect only user level data"), - OPT_BOOLEAN('K', "--all-kernel", &all_kernel, "collect only kernel level data"), + OPT_BOOLEAN('U', "all-user", &all_user, "collect only user level data"), + OPT_BOOLEAN('K', "all-kernel", &all_kernel, "collect only kernel level data"), OPT_END() }; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index fa26865364b6..4ec10e9427d9 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1405,7 +1405,7 @@ static bool dry_run; * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record', * using pipes, etc. */ -struct option __record_options[] = { +static struct option __record_options[] = { OPT_CALLBACK('e', "event", &record.evlist, "event", "event selector. use 'perf list' to list available events", parse_events_option), @@ -1636,7 +1636,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) * overhead. Still generate buildid if they are required * explicitly using * - * perf record --signal-trigger --no-no-buildid \ + * perf record --switch-output --no-no-buildid \ * --no-no-buildid-cache * * Following code equals to: @@ -1687,6 +1687,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) goto out; } + /* Enable ignoring missing threads when -u option is defined. */ + rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX; + err = -ENOMEM; if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0) usage_with_options(record_usage, record_options); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index d2afbe4a240d..06cc759a4597 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -648,7 +648,7 @@ report_parse_ignore_callees_opt(const struct option *opt __maybe_unused, } static int -parse_branch_mode(const struct option *opt __maybe_unused, +parse_branch_mode(const struct option *opt, const char *str __maybe_unused, int unset) { int *branch_mode = opt->value; diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 1a3f1be93372..5b134b0d1ff3 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -200,6 +200,7 @@ struct perf_sched { /* options for timehist command */ bool summary; bool summary_only; + bool idle_hist; bool show_callchain; unsigned int max_stack; bool show_cpu_visual; @@ -208,6 +209,7 @@ struct perf_sched { u64 skipped_samples; const char *time_str; struct perf_time_interval ptime; + struct perf_time_interval hist_time; }; /* per thread run time data */ @@ -230,6 +232,15 @@ struct evsel_runtime { u32 ncpu; /* highest cpu slot allocated */ }; +/* per cpu idle time data */ +struct idle_thread_runtime { + struct thread_runtime tr; + struct thread *last_thread; + struct rb_root sorted_root; + struct callchain_root callchain; + struct callchain_cursor cursor; +}; + /* track idle times per cpu */ static struct thread **idle_threads; static int idle_max_cpu; @@ -1765,7 +1776,7 @@ static u64 perf_evsel__get_time(struct perf_evsel *evsel, u32 cpu) return r->last_time[cpu]; } -static int comm_width = 20; +static int comm_width = 30; static char *timehist_get_commstr(struct thread *thread) { @@ -1807,7 +1818,7 @@ static void timehist_header(struct perf_sched *sched) printf(" "); } - printf(" %-20s %9s %9s %9s", + printf(" %-*s %9s %9s %9s", comm_width, "task name", "wait time", "sch delay", "run time"); printf("\n"); @@ -1820,7 +1831,8 @@ static void timehist_header(struct perf_sched *sched) if (sched->show_cpu_visual) printf(" %*s ", ncpus, ""); - printf(" %-20s %9s %9s %9s\n", "[tid/pid]", "(msec)", "(msec)", "(msec)"); + printf(" %-*s %9s %9s %9s\n", comm_width, + "[tid/pid]", "(msec)", "(msec)", "(msec)"); /* * separator @@ -1830,7 +1842,7 @@ static void timehist_header(struct perf_sched *sched) if (sched->show_cpu_visual) printf(" %.*s ", ncpus, graph_dotted_line); - printf(" %.20s %.9s %.9s %.9s", + printf(" %.*s %.9s %.9s %.9s", comm_width, graph_dotted_line, graph_dotted_line, graph_dotted_line, graph_dotted_line); @@ -1939,39 +1951,40 @@ static void timehist_update_runtime_stats(struct thread_runtime *r, r->total_run_time += r->dt_run; } -static bool is_idle_sample(struct perf_sched *sched, - struct perf_sample *sample, - struct perf_evsel *evsel, - struct machine *machine) +static bool is_idle_sample(struct perf_sample *sample, + struct perf_evsel *evsel) { - struct thread *thread; - struct callchain_cursor *cursor = &callchain_cursor; - /* pid 0 == swapper == idle task */ - if (sample->pid == 0) - return true; + if (strcmp(perf_evsel__name(evsel), "sched:sched_switch") == 0) + return perf_evsel__intval(evsel, sample, "prev_pid") == 0; - if (strcmp(perf_evsel__name(evsel), "sched:sched_switch") == 0) { - if (perf_evsel__intval(evsel, sample, "prev_pid") == 0) - return true; - } + return sample->pid == 0; +} + +static void save_task_callchain(struct perf_sched *sched, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + struct callchain_cursor *cursor = &callchain_cursor; + struct thread *thread; /* want main thread for process - has maps */ thread = machine__findnew_thread(machine, sample->pid, sample->pid); if (thread == NULL) { pr_debug("Failed to get thread for pid %d.\n", sample->pid); - return false; + return; } if (!symbol_conf.use_callchain || sample->callchain == NULL) - return false; + return; if (thread__resolve_callchain(thread, cursor, evsel, sample, NULL, NULL, sched->max_stack + 2) != 0) { if (verbose) error("Failed to resolve callchain. Skipping\n"); - return false; + return; } callchain_cursor_commit(cursor); @@ -1994,8 +2007,24 @@ static bool is_idle_sample(struct perf_sched *sched, callchain_cursor_advance(cursor); } +} + +static int init_idle_thread(struct thread *thread) +{ + struct idle_thread_runtime *itr; + + thread__set_comm(thread, idle_comm, 0); + + itr = zalloc(sizeof(*itr)); + if (itr == NULL) + return -ENOMEM; - return false; + init_stats(&itr->tr.run_stats); + callchain_init(&itr->callchain); + callchain_cursor_reset(&itr->cursor); + thread__set_priv(thread, itr); + + return 0; } /* @@ -2004,7 +2033,7 @@ static bool is_idle_sample(struct perf_sched *sched, */ static int init_idle_threads(int ncpu) { - int i; + int i, ret; idle_threads = zalloc(ncpu * sizeof(struct thread *)); if (!idle_threads) @@ -2018,7 +2047,9 @@ static int init_idle_threads(int ncpu) if (idle_threads[i] == NULL) return -ENOMEM; - thread__set_comm(idle_threads[i], idle_comm, 0); + ret = init_idle_thread(idle_threads[i]); + if (ret < 0) + return ret; } return 0; @@ -2065,14 +2096,23 @@ static struct thread *get_idle_thread(int cpu) idle_threads[cpu] = thread__new(0, 0); if (idle_threads[cpu]) { - idle_threads[cpu]->tid = 0; - thread__set_comm(idle_threads[cpu], idle_comm, 0); + if (init_idle_thread(idle_threads[cpu]) < 0) + return NULL; } } return idle_threads[cpu]; } +static void save_idle_callchain(struct idle_thread_runtime *itr, + struct perf_sample *sample) +{ + if (!symbol_conf.use_callchain || sample->callchain == NULL) + return; + + callchain_cursor__copy(&itr->cursor, &callchain_cursor); +} + /* * handle runtime stats saved per thread */ @@ -2111,7 +2151,7 @@ static struct thread *timehist_get_thread(struct perf_sched *sched, { struct thread *thread; - if (is_idle_sample(sched, sample, evsel, machine)) { + if (is_idle_sample(sample, evsel)) { thread = get_idle_thread(sample->cpu); if (thread == NULL) pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu); @@ -2124,13 +2164,37 @@ static struct thread *timehist_get_thread(struct perf_sched *sched, pr_debug("Failed to get thread for tid %d. skipping sample.\n", sample->tid); } + + save_task_callchain(sched, sample, evsel, machine); + if (sched->idle_hist) { + struct thread *idle; + struct idle_thread_runtime *itr; + + idle = get_idle_thread(sample->cpu); + if (idle == NULL) { + pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu); + return NULL; + } + + itr = thread__priv(idle); + if (itr == NULL) + return NULL; + + itr->last_thread = thread; + + /* copy task callchain when entering to idle */ + if (perf_evsel__intval(evsel, sample, "next_pid") == 0) + save_idle_callchain(itr, sample); + } } return thread; } static bool timehist_skip_sample(struct perf_sched *sched, - struct thread *thread) + struct thread *thread, + struct perf_evsel *evsel, + struct perf_sample *sample) { bool rc = false; @@ -2139,10 +2203,19 @@ static bool timehist_skip_sample(struct perf_sched *sched, sched->skipped_samples++; } + if (sched->idle_hist) { + if (strcmp(perf_evsel__name(evsel), "sched:sched_switch")) + rc = true; + else if (perf_evsel__intval(evsel, sample, "prev_pid") != 0 && + perf_evsel__intval(evsel, sample, "next_pid") != 0) + rc = true; + } + return rc; } static void timehist_print_wakeup_event(struct perf_sched *sched, + struct perf_evsel *evsel, struct perf_sample *sample, struct machine *machine, struct thread *awakened) @@ -2155,8 +2228,8 @@ static void timehist_print_wakeup_event(struct perf_sched *sched, return; /* show wakeup unless both awakee and awaker are filtered */ - if (timehist_skip_sample(sched, thread) && - timehist_skip_sample(sched, awakened)) { + if (timehist_skip_sample(sched, thread, evsel, sample) && + timehist_skip_sample(sched, awakened, evsel, sample)) { return; } @@ -2201,7 +2274,7 @@ static int timehist_sched_wakeup_event(struct perf_tool *tool, /* show wakeups if requested */ if (sched->show_wakeups && !perf_time__skip_sample(&sched->ptime, sample->time)) - timehist_print_wakeup_event(sched, sample, machine, thread); + timehist_print_wakeup_event(sched, evsel, sample, machine, thread); return 0; } @@ -2228,8 +2301,8 @@ static void timehist_print_migration_event(struct perf_sched *sched, if (thread == NULL) return; - if (timehist_skip_sample(sched, thread) && - timehist_skip_sample(sched, migrated)) { + if (timehist_skip_sample(sched, thread, evsel, sample) && + timehist_skip_sample(sched, migrated, evsel, sample)) { return; } @@ -2314,7 +2387,7 @@ static int timehist_sched_change_event(struct perf_tool *tool, goto out; } - if (timehist_skip_sample(sched, thread)) + if (timehist_skip_sample(sched, thread, evsel, sample)) goto out; tr = thread__get_runtime(thread); @@ -2333,7 +2406,7 @@ static int timehist_sched_change_event(struct perf_tool *tool, if (ptime->start && ptime->start > t) goto out; - if (ptime->start > tprev) + if (tprev && ptime->start > tprev) tprev = ptime->start; /* @@ -2350,12 +2423,49 @@ static int timehist_sched_change_event(struct perf_tool *tool, t = ptime->end; } - timehist_update_runtime_stats(tr, t, tprev); + if (!sched->idle_hist || thread->tid == 0) { + timehist_update_runtime_stats(tr, t, tprev); + + if (sched->idle_hist) { + struct idle_thread_runtime *itr = (void *)tr; + struct thread_runtime *last_tr; + + BUG_ON(thread->tid != 0); + + if (itr->last_thread == NULL) + goto out; + + /* add current idle time as last thread's runtime */ + last_tr = thread__get_runtime(itr->last_thread); + if (last_tr == NULL) + goto out; + + timehist_update_runtime_stats(last_tr, t, tprev); + /* + * remove delta time of last thread as it's not updated + * and otherwise it will show an invalid value next + * time. we only care total run time and run stat. + */ + last_tr->dt_run = 0; + last_tr->dt_wait = 0; + last_tr->dt_delay = 0; + + if (itr->cursor.nr) + callchain_append(&itr->callchain, &itr->cursor, t - tprev); + + itr->last_thread = NULL; + } + } if (!sched->summary_only) timehist_print_sample(sched, sample, &al, thread, t); out: + if (sched->hist_time.start == 0 && t >= ptime->start) + sched->hist_time.start = t; + if (ptime->end == 0 || t <= ptime->end) + sched->hist_time.end = t; + if (tr) { /* time of this sched_switch event becomes last time task seen */ tr->last_time = sample->time; @@ -2457,6 +2567,60 @@ static int show_deadthread_runtime(struct thread *t, void *priv) return __show_thread_runtime(t, priv); } +static size_t callchain__fprintf_folded(FILE *fp, struct callchain_node *node) +{ + const char *sep = " <- "; + struct callchain_list *chain; + size_t ret = 0; + char bf[1024]; + bool first; + + if (node == NULL) + return 0; + + ret = callchain__fprintf_folded(fp, node->parent); + first = (ret == 0); + + list_for_each_entry(chain, &node->val, list) { + if (chain->ip >= PERF_CONTEXT_MAX) + continue; + if (chain->ms.sym && chain->ms.sym->ignore) + continue; + ret += fprintf(fp, "%s%s", first ? "" : sep, + callchain_list__sym_name(chain, bf, sizeof(bf), + false)); + first = false; + } + + return ret; +} + +static size_t timehist_print_idlehist_callchain(struct rb_root *root) +{ + size_t ret = 0; + FILE *fp = stdout; + struct callchain_node *chain; + struct rb_node *rb_node = rb_first(root); + + printf(" %16s %8s %s\n", "Idle time (msec)", "Count", "Callchains"); + printf(" %.16s %.8s %.50s\n", graph_dotted_line, graph_dotted_line, + graph_dotted_line); + + while (rb_node) { + chain = rb_entry(rb_node, struct callchain_node, rb_node); + rb_node = rb_next(rb_node); + + ret += fprintf(fp, " "); + print_sched_time(chain->hit, 12); + ret += 16; /* print_sched_time returns 2nd arg + 4 */ + ret += fprintf(fp, " %8d ", chain->count); + ret += callchain__fprintf_folded(fp, chain); + ret += fprintf(fp, "\n"); + } + + return ret; +} + static void timehist_print_summary(struct perf_sched *sched, struct perf_session *session) { @@ -2466,15 +2630,19 @@ static void timehist_print_summary(struct perf_sched *sched, struct thread *t; struct thread_runtime *r; int i; + u64 hist_time = sched->hist_time.end - sched->hist_time.start; memset(&totals, 0, sizeof(totals)); - if (comm_width < 30) - comm_width = 30; - - printf("\nRuntime summary\n"); - printf("%*s parent sched-in ", comm_width, "comm"); - printf(" run-time min-run avg-run max-run stddev migrations\n"); + if (sched->idle_hist) { + printf("\nIdle-time summary\n"); + printf("%*s parent sched-out ", comm_width, "comm"); + printf(" idle-time min-idle avg-idle max-idle stddev migrations\n"); + } else { + printf("\nRuntime summary\n"); + printf("%*s parent sched-in ", comm_width, "comm"); + printf(" run-time min-run avg-run max-run stddev migrations\n"); + } printf("%*s (count) ", comm_width, ""); printf(" (msec) (msec) (msec) (msec) %%\n"); printf("%.117s\n", graph_dotted_line); @@ -2490,7 +2658,7 @@ static void timehist_print_summary(struct perf_sched *sched, printf("<no terminated tasks>\n"); /* CPU idle stats not tracked when samples were skipped */ - if (sched->skipped_samples) + if (sched->skipped_samples && !sched->idle_hist) return; printf("\nIdle stats:\n"); @@ -2504,19 +2672,52 @@ static void timehist_print_summary(struct perf_sched *sched, totals.sched_count += r->run_stats.n; printf(" CPU %2d idle for ", i); print_sched_time(r->total_run_time, 6); - printf(" msec\n"); + printf(" msec (%6.2f%%)\n", 100.0 * r->total_run_time / hist_time); } else printf(" CPU %2d idle entire time window\n", i); } + if (sched->idle_hist && symbol_conf.use_callchain) { + callchain_param.mode = CHAIN_FOLDED; + callchain_param.value = CCVAL_PERIOD; + + callchain_register_param(&callchain_param); + + printf("\nIdle stats by callchain:\n"); + for (i = 0; i < idle_max_cpu; ++i) { + struct idle_thread_runtime *itr; + + t = idle_threads[i]; + if (!t) + continue; + + itr = thread__priv(t); + if (itr == NULL) + continue; + + callchain_param.sort(&itr->sorted_root, &itr->callchain, + 0, &callchain_param); + + printf(" CPU %2d:", i); + print_sched_time(itr->tr.total_run_time, 6); + printf(" msec\n"); + timehist_print_idlehist_callchain(&itr->sorted_root); + printf("\n"); + } + } + printf("\n" " Total number of unique tasks: %" PRIu64 "\n" - "Total number of context switches: %" PRIu64 "\n" - " Total run time (msec): ", + "Total number of context switches: %" PRIu64 "\n", totals.task_count, totals.sched_count); + printf(" Total run time (msec): "); print_sched_time(totals.total_run_time, 2); printf("\n"); + + printf(" Total scheduling time (msec): "); + print_sched_time(hist_time, 2); + printf(" (x %d)\n", sched->max_cpu); } typedef int (*sched_handler)(struct perf_tool *tool, @@ -3036,6 +3237,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('w', "wakeups", &sched.show_wakeups, "Show wakeup events"), OPT_BOOLEAN('M', "migrations", &sched.show_migrations, "Show migration events"), OPT_BOOLEAN('V', "cpu-visual", &sched.show_cpu_visual, "Add CPU visual"), + OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"), OPT_STRING(0, "time", &sched.time_str, "str", "Time span for analysis (start,stop)"), OPT_PARENT(sched_options) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 688dea7cb08f..a02f2e965628 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2195,7 +2195,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused, } static -int process_stat_config_event(struct perf_tool *tool __maybe_unused, +int process_stat_config_event(struct perf_tool *tool, union perf_event *event, struct perf_session *session __maybe_unused) { @@ -2238,7 +2238,7 @@ static int set_maps(struct perf_stat *st) } static -int process_thread_map_event(struct perf_tool *tool __maybe_unused, +int process_thread_map_event(struct perf_tool *tool, union perf_event *event, struct perf_session *session __maybe_unused) { @@ -2257,7 +2257,7 @@ int process_thread_map_event(struct perf_tool *tool __maybe_unused, } static -int process_cpu_map_event(struct perf_tool *tool __maybe_unused, +int process_cpu_map_event(struct perf_tool *tool, union perf_event *event, struct perf_session *session __maybe_unused) { diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh new file mode 100755 index 000000000000..c747bfd7f14d --- /dev/null +++ b/tools/perf/check-headers.sh @@ -0,0 +1,59 @@ +#!/bin/sh + +HEADERS=' +include/uapi/linux/perf_event.h +include/linux/hash.h +include/uapi/linux/hw_breakpoint.h +arch/x86/include/asm/disabled-features.h +arch/x86/include/asm/required-features.h +arch/x86/include/asm/cpufeatures.h +arch/arm/include/uapi/asm/perf_regs.h +arch/arm64/include/uapi/asm/perf_regs.h +arch/powerpc/include/uapi/asm/perf_regs.h +arch/x86/include/uapi/asm/perf_regs.h +arch/x86/include/uapi/asm/kvm.h +arch/x86/include/uapi/asm/kvm_perf.h +arch/x86/include/uapi/asm/svm.h +arch/x86/include/uapi/asm/vmx.h +arch/powerpc/include/uapi/asm/kvm.h +arch/s390/include/uapi/asm/kvm.h +arch/s390/include/uapi/asm/kvm_perf.h +arch/s390/include/uapi/asm/sie.h +arch/arm/include/uapi/asm/kvm.h +arch/arm64/include/uapi/asm/kvm.h +include/asm-generic/bitops/arch_hweight.h +include/asm-generic/bitops/const_hweight.h +include/asm-generic/bitops/__fls.h +include/asm-generic/bitops/fls.h +include/asm-generic/bitops/fls64.h +include/linux/coresight-pmu.h +include/uapi/asm-generic/mman-common.h +' + +check () { + file=$1 + opts= + + shift + while [ -n "$*" ]; do + opts="$opts \"$1\"" + shift + done + + cmd="diff $opts ../$file ../../$file > /dev/null" + + test -f ../../$file && + eval $cmd || echo "Warning: $file differs from kernel" >&2 +} + + +# simple diff check +for i in $HEADERS; do + check $i -B +done + +# diff with extra ignore lines +check arch/x86/lib/memcpy_64.S -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" +check arch/x86/lib/memset_64.S -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" +check include/uapi/asm-generic/mman.h -B -I "^#include <\(uapi/\)*asm-generic/mman-common.h>" +check include/uapi/linux/mman.h -B -I "^#include <\(uapi/\)*asm/mman.h>" diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 9a0236a4cf95..1c27d947c2fe 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -55,6 +55,7 @@ struct record_opts { bool all_user; bool tail_synthesize; bool overwrite; + bool ignore_missing_thread; unsigned int freq; unsigned int mmap_pages; unsigned int auxtrace_mmap_pages; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 23605202d4a1..a77dcc0d24e3 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -186,6 +186,10 @@ static struct test generic_tests[] = { .func = test__thread_map_synthesize, }, { + .desc = "Remove thread map", + .func = test__thread_map_remove, + }, + { .desc = "Synthesize cpu map", .func = test__cpu_map_synthesize, }, diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 0784748f1670..e46723568516 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -42,7 +42,7 @@ LC_NUMERIC=C export LC_COLLATE LC_NUMERIC ifeq ($(srctree),) -srctree := $(patsubst %/,%,$(dir $(shell pwd))) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) srctree := $(patsubst %/,%,$(dir $(srctree))) #$(info Determined 'srctree' to be $(srctree)) endif diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 0d7b251305af..a512f0c8ff5b 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -80,6 +80,7 @@ const char *test__bpf_subtest_get_desc(int subtest); int test__bpf_subtest_get_nr(void); int test_session_topology(int subtest); int test__thread_map_synthesize(int subtest); +int test__thread_map_remove(int subtest); int test__cpu_map_synthesize(int subtest); int test__synthesize_stat_config(int subtest); int test__synthesize_stat(int subtest); diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c index cee2a2cdc933..a4a4b4625ac3 100644 --- a/tools/perf/tests/thread-map.c +++ b/tools/perf/tests/thread-map.c @@ -1,3 +1,4 @@ +#include <stdlib.h> #include <sys/types.h> #include <unistd.h> #include <sys/prctl.h> @@ -93,3 +94,46 @@ int test__thread_map_synthesize(int subtest __maybe_unused) return 0; } + +int test__thread_map_remove(int subtest __maybe_unused) +{ + struct thread_map *threads; + char *str; + int i; + + TEST_ASSERT_VAL("failed to allocate map string", + asprintf(&str, "%d,%d", getpid(), getppid()) >= 0); + + threads = thread_map__new_str(str, NULL, 0); + + TEST_ASSERT_VAL("failed to allocate thread_map", + threads); + + if (verbose) + thread_map__fprintf(threads, stderr); + + TEST_ASSERT_VAL("failed to remove thread", + !thread_map__remove(threads, 0)); + + TEST_ASSERT_VAL("thread_map count != 1", threads->nr == 1); + + if (verbose) + thread_map__fprintf(threads, stderr); + + TEST_ASSERT_VAL("failed to remove thread", + !thread_map__remove(threads, 0)); + + TEST_ASSERT_VAL("thread_map count != 0", threads->nr == 0); + + if (verbose) + thread_map__fprintf(threads, stderr); + + TEST_ASSERT_VAL("failed to not remove thread", + thread_map__remove(threads, 0)); + + for (i = 0; i < threads->nr; i++) + free(threads->map[i].comm); + + free(threads); + return 0; +} diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c index fd710ab33684..af1cfde6b97b 100644 --- a/tools/perf/trace/beauty/mmap.c +++ b/tools/perf/trace/beauty/mmap.c @@ -42,7 +42,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size, P_MMAP_FLAG(SHARED); P_MMAP_FLAG(PRIVATE); +#ifdef MAP_32BIT P_MMAP_FLAG(32BIT); +#endif P_MMAP_FLAG(ANONYMOUS); P_MMAP_FLAG(DENYWRITE); P_MMAP_FLAG(EXECUTABLE); diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index ec7a30fad149..ba36aac340bc 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -215,7 +215,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int ui_browser__set_color(browser, color); if (dl->ins.ops && dl->ins.ops->scnprintf) { if (ins__is_jump(&dl->ins)) { - bool fwd = dl->ops.target.offset > (u64)dl->offset; + bool fwd = dl->ops.target.offset > dl->offset; ui_browser__write_graph(browser, fwd ? SLSMG_DARROW_CHAR : SLSMG_UARROW_CHAR); @@ -245,7 +245,8 @@ static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sy { if (!dl || !dl->ins.ops || !ins__is_jump(&dl->ins) || !disasm_line__has_offset(dl) - || dl->ops.target.offset >= symbol__size(sym)) + || dl->ops.target.offset < 0 + || dl->ops.target.offset >= (s64)symbol__size(sym)) return false; return true; diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 37388397b5bc..18cfcdc90356 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -521,6 +521,12 @@ void perf_hpp_list__register_sort_field(struct perf_hpp_list *list, list_add_tail(&format->sort_list, &list->sorts); } +void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list, + struct perf_hpp_fmt *format) +{ + list_add(&format->sort_list, &list->sorts); +} + void perf_hpp__column_unregister(struct perf_hpp_fmt *format) { list_del(&format->list); @@ -560,6 +566,10 @@ void perf_hpp__setup_output_field(struct perf_hpp_list *list) perf_hpp_list__for_each_sort_list(list, fmt) { struct perf_hpp_fmt *pos; + /* skip sort-only fields ("sort_compute" in perf diff) */ + if (!fmt->entry && !fmt->color) + continue; + perf_hpp_list__for_each_format(list, pos) { if (fmt_equal(fmt, pos)) goto next; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index ea7e0de4b9c1..06cc04e5806a 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -223,13 +223,19 @@ bool ins__is_call(const struct ins *ins) static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map *map __maybe_unused) { const char *s = strchr(ops->raw, '+'); + const char *c = strchr(ops->raw, ','); - ops->target.addr = strtoull(ops->raw, NULL, 16); + if (c++ != NULL) + ops->target.addr = strtoull(c, NULL, 16); + else + ops->target.addr = strtoull(ops->raw, NULL, 16); - if (s++ != NULL) + if (s++ != NULL) { ops->target.offset = strtoull(s, NULL, 16); - else - ops->target.offset = UINT64_MAX; + ops->target.offset_avail = true; + } else { + ops->target.offset_avail = false; + } return 0; } @@ -237,7 +243,7 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op static int jump__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops) { - if (!ops->target.addr) + if (!ops->target.addr || ops->target.offset < 0) return ins__raw_scnprintf(ins, bf, size, ops); return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset); @@ -641,7 +647,8 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr)); - if (addr < sym->start || addr >= sym->end) { + if ((addr < sym->start || addr >= sym->end) && + (addr != sym->end || sym->start != sym->end)) { pr_debug("%s(%d): ERANGE! sym->name=%s, start=%#" PRIx64 ", addr=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__, __LINE__, sym->name, sym->start, addr, sym->end); return -ERANGE; @@ -1205,9 +1212,11 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, if (dl == NULL) return -1; - if (dl->ops.target.offset == UINT64_MAX) + if (!disasm_line__has_offset(dl)) { dl->ops.target.offset = dl->ops.target.addr - map__rip_2objdump(map, sym->start); + dl->ops.target.offset_avail = true; + } /* kcore has no symbols, so add the call target name */ if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.name) { diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 87e4cadc5d27..09776b5af991 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -24,7 +24,8 @@ struct ins_operands { char *raw; char *name; u64 addr; - u64 offset; + s64 offset; + bool offset_avail; } target; union { struct { @@ -68,7 +69,7 @@ struct disasm_line { static inline bool disasm_line__has_offset(const struct disasm_line *dl) { - return dl->ops.target.offset != UINT64_MAX; + return dl->ops.target.offset_avail; } void disasm_line__free(struct disasm_line *dl); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 42922512c1c6..8b610dd9e2f6 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -437,7 +437,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) } call->ip = cursor_node->ip; call->ms.sym = cursor_node->sym; - call->ms.map = cursor_node->map; + call->ms.map = map__get(cursor_node->map); if (cursor_node->branch) { call->branch_count = 1; @@ -477,6 +477,7 @@ add_child(struct callchain_node *parent, list_for_each_entry_safe(call, tmp, &new->val, list) { list_del(&call->list); + map__zput(call->ms.map); free(call); } free(new); @@ -761,6 +762,7 @@ merge_chain_branch(struct callchain_cursor *cursor, list->ms.map, list->ms.sym, false, NULL, 0, 0); list_del(&list->list); + map__zput(list->ms.map); free(list); } @@ -811,7 +813,8 @@ int callchain_cursor_append(struct callchain_cursor *cursor, } node->ip = ip; - node->map = map; + map__zput(node->map); + node->map = map__get(map); node->sym = sym; node->branch = branch; node->nr_loop_iter = nr_loop_iter; @@ -1142,11 +1145,13 @@ static void free_callchain_node(struct callchain_node *node) list_for_each_entry_safe(list, tmp, &node->parent_val, list) { list_del(&list->list); + map__zput(list->ms.map); free(list); } list_for_each_entry_safe(list, tmp, &node->val, list) { list_del(&list->list); + map__zput(list->ms.map); free(list); } @@ -1210,6 +1215,7 @@ int callchain_node__make_parent_list(struct callchain_node *node) goto out; *new = *chain; new->has_children = false; + map__get(new->ms.map); list_add_tail(&new->list, &head); } parent = parent->parent; @@ -1230,6 +1236,7 @@ int callchain_node__make_parent_list(struct callchain_node *node) out: list_for_each_entry_safe(chain, new, &head, list) { list_del(&chain->list); + map__zput(chain->ms.map); free(chain); } return -ENOMEM; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 35c8e379530f..4f4b60f1558a 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -5,6 +5,7 @@ #include <linux/list.h> #include <linux/rbtree.h> #include "event.h" +#include "map.h" #include "symbol.h" #define HELP_PAD "\t\t\t\t" @@ -184,8 +185,13 @@ int callchain_merge(struct callchain_cursor *cursor, */ static inline void callchain_cursor_reset(struct callchain_cursor *cursor) { + struct callchain_cursor_node *node; + cursor->nr = 0; cursor->last = &cursor->first; + + for (node = cursor->first; node != NULL; node = node->next) + map__zput(node->map); } int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip, diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index b2365a63db45..04e536ae4d88 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -990,6 +990,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, * it overloads any global configuration. */ apply_config_terms(evsel, opts); + + evsel->ignore_missing_thread = opts->ignore_missing_thread; } static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) @@ -1419,6 +1421,33 @@ static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, return fprintf(fp, " %-32s %s\n", name, val); } +static bool ignore_missing_thread(struct perf_evsel *evsel, + struct thread_map *threads, + int thread, int err) +{ + if (!evsel->ignore_missing_thread) + return false; + + /* The system wide setup does not work with threads. */ + if (evsel->system_wide) + return false; + + /* The -ESRCH is perf event syscall errno for pid's not found. */ + if (err != -ESRCH) + return false; + + /* If there's only one thread, let it fail. */ + if (threads->nr == 1) + return false; + + if (thread_map__remove(threads, thread)) + return false; + + pr_warning("WARNING: Ignored open failure for pid %d\n", + thread_map__pid(threads, thread)); + return true; +} + static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { @@ -1474,7 +1503,7 @@ retry_sample_id: for (cpu = 0; cpu < cpus->nr; cpu++) { for (thread = 0; thread < nthreads; thread++) { - int group_fd; + int fd, group_fd; if (!evsel->cgrp && !evsel->system_wide) pid = thread_map__pid(threads, thread); @@ -1484,21 +1513,37 @@ retry_open: pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", pid, cpus->map[cpu], group_fd, flags); - FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr, - pid, - cpus->map[cpu], - group_fd, flags); - if (FD(evsel, cpu, thread) < 0) { + fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu], + group_fd, flags); + + FD(evsel, cpu, thread) = fd; + + if (fd < 0) { err = -errno; + + if (ignore_missing_thread(evsel, threads, thread, err)) { + /* + * We just removed 1 thread, so take a step + * back on thread index and lower the upper + * nthreads limit. + */ + nthreads--; + thread--; + + /* ... and pretend like nothing have happened. */ + err = 0; + continue; + } + pr_debug2("\nsys_perf_event_open failed, error %d\n", err); goto try_fallback; } - pr_debug2(" = %d\n", FD(evsel, cpu, thread)); + pr_debug2(" = %d\n", fd); if (evsel->bpf_fd >= 0) { - int evt_fd = FD(evsel, cpu, thread); + int evt_fd = fd; int bpf_fd = evsel->bpf_fd; err = ioctl(evt_fd, diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 6abb89cd27f9..06ef6f29efa1 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -120,6 +120,7 @@ struct perf_evsel { bool tracking; bool per_pkg; bool precise_max; + bool ignore_missing_thread; /* parse modifier helper */ int exclude_GH; int nr_members; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 6770a9645609..7d1b7d33e644 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1,6 +1,7 @@ #include "util.h" #include "build-id.h" #include "hist.h" +#include "map.h" #include "session.h" #include "sort.h" #include "evlist.h" @@ -1019,6 +1020,10 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, int max_stack_depth, void *arg) { int err, err2; + struct map *alm = NULL; + + if (al && al->map) + alm = map__get(al->map); err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent, iter->evsel, al, max_stack_depth); @@ -1058,6 +1063,8 @@ out: if (!err) err = err2; + map__put(alm); + return err; } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index d4b6514eeef5..28c216e3d5b7 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -283,6 +283,8 @@ void perf_hpp_list__column_register(struct perf_hpp_list *list, struct perf_hpp_fmt *format); void perf_hpp_list__register_sort_field(struct perf_hpp_list *list, struct perf_hpp_fmt *format); +void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list, + struct perf_hpp_fmt *format); static inline void perf_hpp__column_register(struct perf_hpp_fmt *format) { @@ -294,6 +296,11 @@ static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format) perf_hpp_list__register_sort_field(&perf_hpp_list, format); } +static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format) +{ + perf_hpp_list__prepend_sort_field(&perf_hpp_list, format); +} + #define perf_hpp_list__for_each_format(_list, format) \ list_for_each_entry(format, &(_list)->fields, list) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index d281ae2b54e8..6a6f44dd594b 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -163,7 +163,7 @@ static struct map *kernel_get_module_map(const char *module) /* A file path -- this is an offline module */ if (module && strchr(module, '/')) - return machine__findnew_module_map(host_machine, 0, module); + return dso__new_map(module); if (!module) module = "kernel"; @@ -173,6 +173,7 @@ static struct map *kernel_get_module_map(const char *module) if (strncmp(pos->dso->short_name + 1, module, pos->dso->short_name_len - 2) == 0 && module[pos->dso->short_name_len - 2] == '\0') { + map__get(pos); return pos; } } @@ -188,15 +189,6 @@ struct map *get_target_map(const char *target, bool user) return kernel_get_module_map(target); } -static void put_target_map(struct map *map, bool user) -{ - if (map && user) { - /* Only the user map needs to be released */ - map__put(map); - } -} - - static int convert_exec_to_group(const char *exec, char **result) { char *ptr1, *ptr2, *exec_copy; @@ -268,21 +260,6 @@ static bool kprobe_warn_out_range(const char *symbol, unsigned long address) } /* - * NOTE: - * '.gnu.linkonce.this_module' section of kernel module elf directly - * maps to 'struct module' from linux/module.h. This section contains - * actual module name which will be used by kernel after loading it. - * But, we cannot use 'struct module' here since linux/module.h is not - * exposed to user-space. Offset of 'name' has remained same from long - * time, so hardcoding it here. - */ -#ifdef __LP64__ -#define MOD_NAME_OFFSET 24 -#else -#define MOD_NAME_OFFSET 12 -#endif - -/* * @module can be module name of module file path. In case of path, * inspect elf and find out what is actual module name. * Caller has to free mod_name after using it. @@ -296,6 +273,7 @@ static char *find_module_name(const char *module) Elf_Data *data; Elf_Scn *sec; char *mod_name = NULL; + int name_offset; fd = open(module, O_RDONLY); if (fd < 0) @@ -317,7 +295,21 @@ static char *find_module_name(const char *module) if (!data || !data->d_buf) goto ret_err; - mod_name = strdup((char *)data->d_buf + MOD_NAME_OFFSET); + /* + * NOTE: + * '.gnu.linkonce.this_module' section of kernel module elf directly + * maps to 'struct module' from linux/module.h. This section contains + * actual module name which will be used by kernel after loading it. + * But, we cannot use 'struct module' here since linux/module.h is not + * exposed to user-space. Offset of 'name' has remained same from long + * time, so hardcoding it here. + */ + if (ehdr.e_ident[EI_CLASS] == ELFCLASS32) + name_offset = 12; + else /* expect ELFCLASS64 by default */ + name_offset = 24; + + mod_name = strdup((char *)data->d_buf + name_offset); ret_err: elf_end(elf); @@ -412,7 +404,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, } out: - put_target_map(map, uprobes); + map__put(map); return ret; } @@ -618,6 +610,67 @@ error: return ret ? : -ENOENT; } +/* Adjust symbol name and address */ +static int post_process_probe_trace_point(struct probe_trace_point *tp, + struct map *map, unsigned long offs) +{ + struct symbol *sym; + u64 addr = tp->address + tp->offset - offs; + + sym = map__find_symbol(map, addr); + if (!sym) + return -ENOENT; + + if (strcmp(sym->name, tp->symbol)) { + /* If we have no realname, use symbol for it */ + if (!tp->realname) + tp->realname = tp->symbol; + else + free(tp->symbol); + tp->symbol = strdup(sym->name); + if (!tp->symbol) + return -ENOMEM; + } + tp->offset = addr - sym->start; + tp->address -= offs; + + return 0; +} + +/* + * Rename DWARF symbols to ELF symbols -- gcc sometimes optimizes functions + * and generate new symbols with suffixes such as .constprop.N or .isra.N + * etc. Since those symbols are not recorded in DWARF, we have to find + * correct generated symbols from offline ELF binary. + * For online kernel or uprobes we don't need this because those are + * rebased on _text, or already a section relative address. + */ +static int +post_process_offline_probe_trace_events(struct probe_trace_event *tevs, + int ntevs, const char *pathname) +{ + struct map *map; + unsigned long stext = 0; + int i, ret = 0; + + /* Prepare a map for offline binary */ + map = dso__new_map(pathname); + if (!map || get_text_start_address(pathname, &stext) < 0) { + pr_warning("Failed to get ELF symbols for %s\n", pathname); + return -EINVAL; + } + + for (i = 0; i < ntevs; i++) { + ret = post_process_probe_trace_point(&tevs[i].point, + map, stext); + if (ret < 0) + break; + } + map__put(map); + + return ret; +} + static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, int ntevs, const char *exec) { @@ -645,18 +698,31 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, return ret; } -static int add_module_to_probe_trace_events(struct probe_trace_event *tevs, - int ntevs, const char *module) +static int +post_process_module_probe_trace_events(struct probe_trace_event *tevs, + int ntevs, const char *module, + struct debuginfo *dinfo) { + Dwarf_Addr text_offs = 0; int i, ret = 0; char *mod_name = NULL; + struct map *map; if (!module) return 0; - mod_name = find_module_name(module); + map = get_target_map(module, false); + if (!map || debuginfo__get_text_offset(dinfo, &text_offs, true) < 0) { + pr_warning("Failed to get ELF symbols for %s\n", module); + return -EINVAL; + } + mod_name = find_module_name(module); for (i = 0; i < ntevs; i++) { + ret = post_process_probe_trace_point(&tevs[i].point, + map, (unsigned long)text_offs); + if (ret < 0) + break; tevs[i].point.module = strdup(mod_name ? mod_name : module); if (!tevs[i].point.module) { @@ -666,6 +732,8 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs, } free(mod_name); + map__put(map); + return ret; } @@ -679,7 +747,8 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, /* Skip post process if the target is an offline kernel */ if (symbol_conf.ignore_vmlinux_buildid) - return 0; + return post_process_offline_probe_trace_events(tevs, ntevs, + symbol_conf.vmlinux_name); reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { @@ -722,7 +791,7 @@ arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unuse static int post_process_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event *tevs, int ntevs, const char *module, - bool uprobe) + bool uprobe, struct debuginfo *dinfo) { int ret; @@ -730,7 +799,8 @@ static int post_process_probe_trace_events(struct perf_probe_event *pev, ret = add_exec_to_probe_trace_events(tevs, ntevs, module); else if (module) /* Currently ref_reloc_sym based probe is not for drivers */ - ret = add_module_to_probe_trace_events(tevs, ntevs, module); + ret = post_process_module_probe_trace_events(tevs, ntevs, + module, dinfo); else ret = post_process_kernel_probe_trace_events(tevs, ntevs); @@ -774,30 +844,27 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, } } - debuginfo__delete(dinfo); - if (ntevs > 0) { /* Succeeded to find trace events */ pr_debug("Found %d probe_trace_events.\n", ntevs); ret = post_process_probe_trace_events(pev, *tevs, ntevs, - pev->target, pev->uprobes); + pev->target, pev->uprobes, dinfo); if (ret < 0 || ret == ntevs) { + pr_debug("Post processing failed or all events are skipped. (%d)\n", ret); clear_probe_trace_events(*tevs, ntevs); zfree(tevs); + ntevs = 0; } - if (ret != ntevs) - return ret < 0 ? ret : ntevs; - ntevs = 0; - /* Fall through */ } + debuginfo__delete(dinfo); + if (ntevs == 0) { /* No error but failed to find probe point. */ pr_warning("Probe point '%s' not found.\n", synthesize_perf_probe_point(&pev->point)); return -ENOENT; - } - /* Error path : ntevs < 0 */ - pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs); - if (ntevs < 0) { + } else if (ntevs < 0) { + /* Error path : ntevs < 0 */ + pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs); if (ntevs == -EBADF) pr_warning("Warning: No dwarf info found in the vmlinux - " "please rebuild kernel with CONFIG_DEBUG_INFO=y.\n"); @@ -2869,7 +2936,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } out: - put_target_map(map, pev->uprobes); + map__put(map); free(syms); return ret; @@ -3362,10 +3429,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter, return ret; /* Get a symbol map */ - if (user) - map = dso__new_map(target); - else - map = kernel_get_module_map(target); + map = get_target_map(target, user); if (!map) { pr_err("Failed to get a map for %s\n", (target) ? : "kernel"); return -EINVAL; @@ -3397,9 +3461,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter, } end: - if (user) { - map__put(map); - } + map__put(map); exit_probe_symbol_maps(); return ret; diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index df4debe564da..0d9d6e0803b8 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1501,7 +1501,8 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg, } /* For the kernel module, we need a special code to get a DIE */ -static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs) +int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs, + bool adjust_offset) { int n, i; Elf32_Word shndx; @@ -1530,6 +1531,8 @@ static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs) if (!shdr) return -ENOENT; *offs = shdr->sh_addr; + if (adjust_offset) + *offs -= shdr->sh_offset; } } return 0; @@ -1543,16 +1546,12 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, Dwarf_Addr _addr = 0, baseaddr = 0; const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp; int baseline = 0, lineno = 0, ret = 0; - bool reloc = false; -retry: + /* We always need to relocate the address for aranges */ + if (debuginfo__get_text_offset(dbg, &baseaddr, false) == 0) + addr += baseaddr; /* Find cu die */ if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) { - if (!reloc && debuginfo__get_text_offset(dbg, &baseaddr) == 0) { - addr += baseaddr; - reloc = true; - goto retry; - } pr_warning("Failed to find debug information for address %lx\n", addr); ret = -EINVAL; diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index f1d8558f498e..2956c5198652 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -46,6 +46,9 @@ int debuginfo__find_trace_events(struct debuginfo *dbg, int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, struct perf_probe_point *ppt); +int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs, + bool adjust_offset); + /* Find a line range */ int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 99400b0e8f2a..adbc6c02c3aa 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -537,6 +537,12 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size) break; } else { int n = namesz + descsz; + + if (n > (int)sizeof(bf)) { + n = sizeof(bf); + pr_debug("%s: truncating reading of build id in sysfs file %s: n_namesz=%u, n_descsz=%u.\n", + __func__, filename, nhdr.n_namesz, nhdr.n_descsz); + } if (read(fd, bf, n) != n) break; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index df2482b2ba45..dc93940de351 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1459,7 +1459,8 @@ int dso__load(struct dso *dso, struct map *map) * Read the build id if possible. This is required for * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work */ - if (is_regular_file(dso->long_name) && + if (!dso->has_build_id && + is_regular_file(dso->long_name) && filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) dso__set_build_id(dso, build_id); diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 40585f5b7027..f9eab200fd75 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -448,3 +448,25 @@ bool thread_map__has(struct thread_map *threads, pid_t pid) return false; } + +int thread_map__remove(struct thread_map *threads, int idx) +{ + int i; + + if (threads->nr < 1) + return -EINVAL; + + if (idx >= threads->nr) + return -EINVAL; + + /* + * Free the 'idx' item and shift the rest up. + */ + free(threads->map[idx].comm); + + for (i = idx; i < threads->nr - 1; i++) + threads->map[i] = threads->map[i + 1]; + + threads->nr--; + return 0; +} diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index bd3b971588da..ea0ef08c6303 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -58,4 +58,5 @@ static inline char *thread_map__comm(struct thread_map *map, int thread) void thread_map__read_comms(struct thread_map *threads); bool thread_map__has(struct thread_map *threads, pid_t pid); +int thread_map__remove(struct thread_map *threads, int idx); #endif /* __PERF_THREAD_MAP_H */ |